Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    solve for variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     аласыз
    0.45
     империи
    0.44
     चुनावों
    0.43
     уены
    0.42
    tk
    0.42
    neigh
    0.41
    ्यादा
    0.41
    neighbours
    0.41
     विनाश
    0.41
    谎
    0.40
    POSITIVE LOGITS
     emergent
    0.58
     interdependent
    0.43
     emerging
    0.42
     variables
    0.41
     auricul
    0.41
     β
    0.40
     VARIABLES
    0.39
    חד
    0.39
     POR
    0.39
     Variablen
    0.38
    Act Density 0.035%

    No Known Activations